© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77929
    Prev
    Next
    INDEX
    Explanations

    grip and rubber

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron highlights technical product‐feature language—phrases that list engineered specifications, materials, finishes, and functional attributes.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pense
    -0.80
    ネマ
    -0.77
    ੭
    -0.72
    pkl
    -0.72
    raham
    -0.70
     jang
    -0.69
    Unsubscribe
    -0.69
    ʖ
    -0.69
    twitter
    -0.68
     آهنگ
    -0.68
    POSITIVE LOGITS
     grip
    2.13
     rubber
    1.83
     slippery
    1.81
     antidesliz
    1.77
     Grip
    1.73
    grip
    1.64
     slip
    1.64
     grips
    1.62
     traction
    1.59
    Grip
    1.53
    Activations Density 0.032%

    No Known Activations